© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99074
    Prev
    Next
    INDEX
    Explanations

    water projects, supply, and management

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron is specialized to pick up occurrences of the word “water” (and its compounds) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selesai
    -0.82
     kilomètres
    -0.82
    niu
    -0.82
    ポケット
    -0.81
     leeren
    -0.80
     komik
    -0.79
    льников
    -0.79
     weichen
    -0.79
     ثلاث
    -0.79
     черно
    -0.77
    POSITIVE LOGITS
     supply
    1.89
     resources
    1.34
     resource
    1.17
     management
    1.16
     Supply
    1.13
    supply
    1.09
     supplies
    0.98
     supplied
    0.96
     September
    0.93
     distribution
    0.92
    Activations Density 0.012%

    No Known Activations